R Visualization Exercises

Programming for Data Science Bootcamp

Import Libraries

library(vctrs)

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.1     ✔ tibble    3.2.1
✔ lubridate 1.9.4     ✔ tidyr     1.3.1
✔ purrr     1.0.4     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::data_frame() masks tibble::data_frame(), vctrs::data_frame()
✖ dplyr::filter()     masks stats::filter()
✖ dplyr::lag()        masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Get Data

See info on the mpg dataset.

head(mpg)

A tibble: 6 × 11

manufacturer	model	displ	year	cyl	trans	drv	cty	hwy	fl	class
<chr>	<chr>	<dbl>	<int>	<int>	<chr>	<chr>	<int>	<int>	<chr>	<chr>
audi	a4	1.8	1999	4	auto(l5)	f	18	29	p	compact
audi	a4	1.8	1999	4	manual(m5)	f	21	29	p	compact
audi	a4	2.0	2008	4	manual(m6)	f	20	31	p	compact
audi	a4	2.0	2008	4	auto(av)	f	21	30	p	compact
audi	a4	2.8	1999	6	auto(l5)	f	16	26	p	compact
audi	a4	2.8	1999	6	manual(m5)	f	18	26	p	compact

Exercise 1

Run mpg %>% ggplot() what do you see?

mpg %>% ggplot()

Exercise 2

Make a scatter plot of hwy vs. cyl in the mpg data set.

mpg %>%
    ggplot(aes(x = cyl, y = hwy)) +
      geom_point()

aes is actually a value for the mapping argument.

mpg %>%
    ggplot(mapping = aes(x = cyl, y = hwy)) +
      geom_point()

aes can also be treated as a separate operation.

mpg %>%
    ggplot() +
    aes(x = cyl, y = hwy) +
    geom_point()

Exercise 3

What happens if you make a scatter plot of class vs drv?

Why is the plot not useful?

mpg %>% 
    ggplot(aes(x = class, y = drv)) + 
    geom_point()

The resulting scatterplot has only a few points.

A scatter plot is not a useful display of these variables since both drv and class are categorical variables.

👉 Categorical variables typically take a small number of values, so there are a limited number of unique combinations of $(x, y)$ values that can be displayed.

👉 In this data, drv takes $3$ values and class takes $7$ values, meaning that there are only $21$ values that could be plotted on a scatterplot of drv vs. class.

👉 In this data, there $12$ values of (drv, class) are observed.

Exercise 4

Plot the mathematical function $sin(x)/x$.

Hint: Use this to create your data and convert to a data frame or tibble:

x <- seq(-6 * pi, 6 * pi, length.out = 100)

x <- seq(-6 * pi, 6 * pi, length.out = 100)
dat <- data.frame(x = x, y = sin(x)/x)
head(dat)

A data.frame: 6 × 2

	x	y
	<dbl>	<dbl>
1	-18.84956	-3.898172e-17
2	-18.46876	-2.012385e-02
3	-18.08796	-3.815130e-02
4	-17.70716	-5.137086e-02
5	-17.32636	-5.765016e-02
6	-16.94556	-5.576687e-02

ggplot(data = dat, 
    mapping = aes(x = x, y = y)) + 
    geom_line()

dat %>% 
    ggplot(aes(x = x, y = y)) + 
    geom_line()

Exercise 5

Plot the cars data set as a scatter plot using speed vs dist.

cars %>% 
    ggplot(aes(x = speed, y = dist)) +
    geom_point()

Exercise 6

Create the same plot plot, this time using color to distinguish data points with distances taken to stop greater than $80$.

head(cars)

A data.frame: 6 × 2

	speed	dist
	<dbl>	<dbl>
1	4	2
2	4	10
3	7	4
4	7	22
5	8	16
6	9	10

cars %>%
    ggplot(aes(x = speed, y = dist)) +
    geom_point(mapping = aes(color = dist > 80))

cars %>%
    ggplot() +
    aes(x = speed, y = dist) +
    geom_point() +
    aes(color = dist > 80)

Exercise 7

Change the plot so that values $> 80$ are in red and the other in blue.

Hint: Define the colors using a manual color scale in scale_color_manual().

cars %>%
    ggplot(aes(x = speed, y = dist)) + 
    geom_point(mapping = aes(color = dist > 80)) + 
    scale_color_manual(values = c("blue", "red"))

Another way, using ifelse():

cars %>%
    ggplot(aes(speed, dist)) + 
    geom_point(color = ifelse(cars$dist > 80, 'red', 'blue'))

Exercise 8

Add a second geom that produces a smoothed line.

Use lm as your smoothing method.

Hint: Add geom_smooth() to your graphic.

cars %>%
    ggplot(aes(x = speed, y = dist)) + 
      geom_point(aes(color = dist > 80)) + 
      scale_color_manual(values = c("black", "red")) +
      geom_smooth(method = 'lm')

`geom_smooth()` using formula = 'y ~ x'

Smoothing method (function) to use includes: lm, glm, gam, loess, rlm.

loess: locally weighted smoothing

cars %>%
    ggplot(aes(x = speed, y = dist)) + 
      geom_point(aes(color = dist > 80)) + 
      scale_color_manual(values = c("black", "red")) +
      geom_smooth(method = 'loess')

`geom_smooth()` using formula = 'y ~ x'

Exercise 9

Plot histograms for speed and dist in cars.

cars %>%
    ggplot(aes(x = speed)) + 
    geom_histogram(bins = 10)

cars %>%
    ggplot(aes(x = dist)) + 
    geom_histogram(bins = 10)

Exercise 10

Create a faceted plot of a scatterplot of hwy and cty of the mpg with drv as rows and cyl as cols.

What do the empty cells mean?

mpg %>% 
    ggplot() +
      geom_point(aes(x = hwy, y = cty)) +
      facet_grid(drv ~ cyl)

The empty cells (facets) in this plot are combinations of drv and cyl that have no observations.

These are the same locations in the scatter plot of drv and cyl that have no points.

mpg %>% 
    ggplot() +
      geom_point(aes(y = drv, x = cyl))

Without faceting:

mpg %>% 
    ggplot() +
      geom_point(aes(x = hwy, y = cty, 
                     color=drv, 
                     shape=as.factor(cyl)))

Exercise 11

Reproduce this graphic from the iris dataset:

Hint: This graphic uses two geometries, one title, and one theme function.

One of the geometries is geom_density2d() and the theme function is theme_light().

iris %>%
  ggplot(aes(x = Sepal.Length, y = Sepal.Width, color = Species, shape = Species)) +
  geom_point() +
  geom_density2d() +
  ggtitle('IRIS') +
  theme_light()

Exercise 12

Reproduce this graphc from the iris dataset:

Hints:

(1) Preprocess your data as follows:

{r}
iris %>%
  mutate(Species = 'ALL') %>%   # Create a copy of iris where Species has only 'ALL'
  bind_rows(iris)               # concatenate to the original iris

(2) This graphic uses faceting with facet_wrap() and theme function theme_bw().

iris %>%
  mutate(Species = 'ALL') %>%
  bind_rows(iris) %>%
  ggplot(aes(x = Petal.Length, y = Petal.Width, color = Species)) +
      geom_point() +
      geom_smooth(method = 'loess') +
      xlab('Petal Length') +
      ylab('Petal Width') +
      facet_wrap(~Species, scales = 'free') +
      theme_bw()

`geom_smooth()` using formula = 'y ~ x'

Exercise 13

Reproduce this graphic using the mtcars dataset:

mtcars %>%
  rownames_to_column() %>%
  mutate(rowname = forcats::fct_reorder(rowname, mpg)) %>%
  ggplot(aes(rowname, mpg, label = rowname)) +
  geom_point() +
  geom_text(nudge_y = .3, hjust = 'left') +
  coord_flip() +
  ylab('Miles per gallon fuel consumption') +
  ylim(10, 40) +
  theme_classic() +
  theme(plot.title = element_text(hjust = 0, size = 16),
        axis.title.x = element_text(face = 'bold'),
        axis.title.y = element_blank(),
        axis.text.y = element_blank(),
        axis.ticks.y = element_blank(),
        axis.line.y = element_blank())

Exercise 14

Reproduce this graphic using the mtcars dataset:

mtcars %>%
  ggplot(aes(x = mpg, y = qsec, size = disp, color = as.factor(am))) +
  geom_point() +
  scale_colour_discrete(name  ="Gear",
                        breaks=c(0, 1),
                        labels=c("Manual", "Automatic")) +
  scale_size_continuous(name = 'Displacement') +
  xlab('Miles per gallon') +
  ylab('1/4 mile time') +
  theme_light()

Exercise 15

Reproduce this image using the diamonds dataset:

https://www.r-exercises.com/wp-content/uploads/2018/02/ggplot-exercises-5.png

Process the data.

diamonds2plot <- diamonds %>%
  group_by(cut, color) %>%
  # See note re .groups in the following
  summarize(price = mean(price), .groups = 'drop') %>% 
  arrange(color, price) %>%
  ungroup() %>%
  mutate(id = row_number(), 
         angle = 90 - 360 * (id - 0.5) / n())

Note the we add the .groups = 'drop' argument to summarize() to avoid this error message:

• summarise() has grouped output by 'cut'. You can override using the .groups argument.

Build the visualization.

diamonds2plot  %>%
  ggplot(aes(factor(id), price, fill = color, group = cut, label = cut)) +
  geom_bar(stat = 'identity', position = 'dodge') +
  geom_text(hjust = 0, angle = diamonds2plot$angle, alpha = .5) +
  coord_polar() +
  ggtitle('Mean dimond price') +
  ylim(-3000, 7000) +
  theme_void() +
  theme(plot.title = element_text(hjust = 0.5, size = 16, face = 'bold'))